Integrating recommendation models for improved web page prediction accuracy

ABSTRACT

Recent research initiatives have addressed the need for improved performance of Web page prediction accuracy that would profit many applications, e-business in particular. Different Web usage mining frameworks have been implemented for this purpose specifically Association rules, clustering, and Markov model. Each of these frameworks has its own strengths and weaknesses and it has been proved that using each of these frameworks individually does not provide a suitable solution that answers today's Web page prediction needs. This paper endeavors to provide an improved Web page prediction accuracy by using a novel approach that involves integrating clustering, association rules and Markov models according to some constraints. Experimental results prove that this integration provides better prediction accuracy than using each technique individually.

References

1. Adami, G., Avesani, P. & Sona, D. (2003), 'Clustering documents in a web directory', WIDM'03, USA pp. 66--73.
2. Agrawal, R. & Srikant, R. (1994), 'Fast algorithms for mining association rules', VLDB'94, Chile pp. 487--499.
3. Bouras, C. & Konidaris, A. (2004), 'Predictive prefetching on the web and its potential impact in the wide area', WWW: Internet and Web Information Systems (7), 143--179.
4. Cadez, I., Heckerman, D., Meek, C., Smyth, P. & White, S. (2003), 'Model-based clustering and visualization of navigation patterns on a web site', Data Mining and Knowledge Discovery 7.
5. Casale, G. (2005), 'Combining queueing networks and web usage mining techniques for web performance analysis', ACM Symposium on Applied Computing pp. 1699--1703.
6. chen, M., LaPaugh, A. S. & Singh, J. P. (2002), 'Predicting category accesses for a user in a structured information space', SIGIR'02, Finland pp. 65--72.
7. Deshpande, M. & Karypis, G. (2004), 'Selective markov models for predicting web page accesses', Transactions on Internet Technology 4(2), 163--184.
8. Eick, C. F., Zeidat, N. & Zhao, Z. (2004), 'Supervised clustering - algorithms and benefits', IEEE ICTAI'04 pp. 774--776.
9. Eirinaki, M., Vazirgiannis, M. & Kapogiannis, D. (2005), 'Web path recommendations based on page ranking and markov models', WIDM'05 pp. 2--9.
10. Halkidi, M., Nguyen, B., Varlamis, I. & Vazirgiannis, M. (2003), 'Thesus: Organizing web document collections based on link semantics', The VLDB Journal 2003(12), 320--332.
11. Jain, A. K., Murty, M. N. & Flynn, P. J. (1999), 'Data clustering: A review', ACM Computing Surveys 31(3), 264--323.
12. Kim, D., Adam, N., Alturi, V., Bieber, M. & Yesha, Y. (2004), 'A clickstream-based collaborative filtering personalization model: Towards a better performance', WIDM '04 pp. 88--95.
13. Lai, H. & Yang, T. C. (2000), 'A group-based inference approach to customized marketing on the web - integrating clustering and association rules techniques', Hawaii International Conference on System Sciences pp. 37--46.
14. Liu, F., Lu, Z. & Lu, S. (2001), 'Mining association rules using clustering', Intelligent Data Analysis (5), 309--326.
15. Lu, L., Dunham, M. & Meng, Y. (2005), 'Discovery of significant usage patterns from clusters of click-stream data', WebKDD '05.
16. Mathur, V. & Apte, V. (2007), 'An overhead and resource contention aware analytical model for over-loaded web servers', WOSP'07, Argentina.
17. Mobasher, B., Dai, H., Luo, T. & Nakagawa, M. (2001), 'Effective personalization based on association rule discovery from web usage data', WIDM'01, USA pp. 9--15.
18. Papadakis, N. K. & Skoutas, D. (2005), 'STAVIES: A system for information extraction from unknown web data sources through automatic web warpper generation using clustering techniques', IEEE Transactions on Knowledge and Data Engineering 17(12), 1638--1652.
19. Pitkow, J. & Pirolli, P. (1999), 'Mining longest repeating subsequences to predict www surfing', USENIX Annual Technical Conference pp. 139--150.
20. Pons, A. P. (2006), 'Object prefetching using semantic links', The DATA BASE for Advances in Information Systems 37(1), 97--109.
21. Rigou, M., Sirmakesses, S. & Tzimas, G. (2006), 'A method for personalized clustering in data intensive web applications', APS'06, Denmark pp. 35--40.
22. Sarukkai, R. (2000), 'Link prediction and path analysis using markov chains', 9th International WWW Conference, Amsterdam pp. 377--386.
23. Spiliopoulou, M., Faulstich, L. C. & Winkler, K. (1999), 'A data miner analysing the navigational behaviour of web users', Workshop on Machine Learning in User Modelling of the ACAI'99, Greece.
24. Srivastava, J., Cooley, R., Deshpande, M. & Tan, P. (2000), 'Web usage mining: Discovery and applications of usage patterns from web data.', SIGDD Explorations 1(2), 12--23.
25. Strehl, A., Ghosh, J. & Mooney, R. J. (2000), 'Impact of similarity measures on web-page clustering', AI for Web Search pp. 58--64.
26. Wang, Q., Makaroff, D. J. & Edwards, H. K. (2004), 'Characterizing customer groups for an e-commerce website', EC'04, USA pp. 218--227.
27. Yang, Q., Li, T. & Wang, K. (2004), 'Building association-rule based sequential classifiers for web-document prediction', Journal of Data Mining and Knowledge Discovery 8.
28. Yong, W., Zhanhuai, L. & Yang, Z. (2005), 'Mining sequential association-rule for improving web document prediction', ICCIMA'05 pp. 146--151.
29. Zhao, Q., Bhomick, S. S. & Gruenwald, L. (2005), 'Wam miner: In the search of web access motifs from historical web log data', CIKM'05, Germany pp. 421--428.
30. Zhong, S. & Ghosh, J. (2003), 'A unified framework for model-based clustering', Machine Learning Research 4, 1001--1037.
31. Zhu, J., Hong, J. & Hughes, J. G. (2002), 'Using markov models for web site link prediction', HT'02, USA pp. 169--170.

Index Terms

• Applied computing

• Computing methodologies

  • Machine learning

• Information systems

  • Information retrieval

    • Retrieval tasks and goals

      • Document filtering

  • Information systems applications

    • Data mining

  • World Wide Web